Papers

New on arXiv

Sat 13 Jul 2024

109 papers

An Autonomous GIS Agent Framework for Geospatial Data RetrievalLLM agents and tool use → Multimodal and embodied agents
Deep deterministic policy gradient with symmetric data augmentation for lateral attitude tracking control of a fixed-wing aircraftDeep reinforcement learning methods → RL for robot locomotion and manipulation
AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligenceLLM agents and tool use → Medical and scientific domain agents
Document-level Clinical Entity and Relation Extraction via Knowledge Base-Guided GenerationRetrieval-augmented generation → Medical and biomedical RAG
Curriculum Is More Influential Than Haptic Information During Reinforcement Learning of Object Manipulation Against GravityDeep reinforcement learning methods → RL for robot locomotion and manipulation
A Training Data Recipe to Accelerate A* Search with Language ModelsLLM reasoning → Test-time compute and efficient thinking
Hydra: Bidirectional State Space Models Through Generalized Matrix MixersState-space sequence models (S4, Mamba) → Core SSM architectures for language
DiffRect: Latent Diffusion Label Rectification for Semi-supervised Medical Image SegmentationDiffusion models → Medical imaging and segmentation
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient MethodsDeep reinforcement learning methods → RL theory and sample complexity
Cohesive Conversations: Enhancing Authenticity in Multi-Agent Simulated DialoguesLLM agents and tool use → General LLM agent frameworks and benchmarks
PSC: Posterior Sampling-Based CompressionDiffusion models → Diffusion for compression and wireless
Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization ModelingLLM reasoning → Test-time compute and efficient thinking
Model-free Distortion Canceling and Control of Quantum DevicesDeep reinforcement learning methods → Quantum reinforcement learning
Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
VLMPC: Vision-Language Model Predictive Control for Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
3D Weakly Supervised Semantic Segmentation with 2D Vision-Language GuidanceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data AnalysisLLM agents and tool use → Medical and scientific domain agents
Dense Multimodal Alignment for Open-Vocabulary 3D Scene UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Prototype Clustered Diffusion Models for Versatile Inverse ProblemsDiffusion models → Inverse problems and image restoration
Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and SynthesisState-space sequence models (S4, Mamba) → Speech and audio SSMs
Partial-differential-algebraic equations of nonlinear dynamics by Physics-Informed Neural-Network: (I) Operator splitting and framework assessment
Bilingual Adaptation of Monolingual Foundation Models
Beyond KV Caching: Shared Attention for Efficient LLMs
A Survey of Distance-Based Vessel Trajectory Clustering: Data Pre-processing, Methodologies, Applications, and Experimental Evaluation
Empowering Graph Invariance Learning with Deep Spurious Infomax
Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning
Generating In-store Customer Journeys from Scratch with GPT Architectures
Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator
Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viability
ST-RetNet: A Long-term Spatial-Temporal Traffic Flow Prediction Method
SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
Causality extraction from medical text using Large Language Models (LLMs)
Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks
Identification of Average Causal Effects in Confounded Additive Noise Models
Sim-to-Real Domain Adaptation for Deformation Classification
Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
A Dynamic Algorithm for Weighted Submodular Cover Problem
Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies
Pay Less On Clinical Images: Asymmetric Multi-Modal Fusion Method For Efficient Multi-Label Skin Lesion Classification
Distributed computing for physics-based data-driven reduced modeling at scale: Application to a rotating detonation rocket engine
PFPs: Prompt-guided Flexible Pathological Segmentation for Diverse Potential Outcomes Using Large Vision and Language Models
MedLeak: Multimodal Medical Data Leakage in Secure Federated Learning with Crafted Models
Optimizing ROI Benefits Vehicle ReID in ITS
Learning Online Scale Transformation for Talking Head Video Generation
TrIM: Transformed Iterative Mondrian Forests for Gradient-based Dimension Reduction and High-Dimensional Regression
Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning
LFFR: Logistic Function For (single-output) Regression
PSO Fuzzy XGBoost Classifier Boosted with Neural Gas Features on EEG Signals in Emotion Recognition
Low-Rank Interconnected Adaptation across Layers
Minimizing PLM-Based Few-Shot Intent Detectors
WojoodNER 2024: The Second Arabic Named Entity Recognition Shared Task
LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation
Evaluating the Impact of Different Quantum Kernels on the Classification Performance of Support Vector Machine Algorithm: A Medical Dataset Application
Metric Learning for Clifford Group Equivariant Neural Networks
Region-aware Image-based Human Action Retrieval with Transformers
MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection
Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors
Emotion Detection through Body Gesture and Face
SensEmo: Enabling Affective Learning through Real-time Emotion Recognition with Smartwatches
Learning a Mini-batch Graph Transformer via Two-stage Interaction Augmentation
Transferring Structure Knowledge: A New Task to Fake news Detection Towards Cold-Start Propagation
NamedCurves: Learned Image Enhancement via Color Naming
FarFetched: Entity-centric Reasoning and Claim Validation for the Greek Language based on Textually Represented Environments
Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation
sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting
SeFi-CD: A Semantic First Change Detection Paradigm That Can Detect Any Change You Want
Resource Management for Low-latency Cooperative Fine-tuning of Foundation Models at the Network Edge
ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistency
A Systematic Survey of Natural Language Processing for the Greek Language
IFTR: An Instance-Level Fusion Transformer for Visual Collaborative Perception
Building pre-train LLM Dataset for the INDIC Languages: a case study on Hindi
Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation
Free-form Grid Structure Form Finding based on Machine Learning and Multi-objective Optimisation
Text-Based Detection of On-Hold Scripts in Contact Center Calls
Towards Understanding Epoch-wise Double descent in Two-layer Linear Neural Networks
Eliminating Feature Ambiguity for Few-Shot Segmentation
Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis
LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment
Size and Smoothness Aware Adaptive Focal Loss for Small Tumor Segmentation
NativQA: Multilingual Culturally-Aligned Natural Query for LLMs
VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation
AraFinNLP 2024: The First Arabic Financial NLP Shared Task
Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System
Preserving the Privacy of Reward Functions in MDPs through Deception
Asynchronous Feedback Network for Perceptual Point Cloud Quality Assessment
IoT-LM: Large Multisensory Language Models for the Internet of Things
ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs
Convex space learning for tabular synthetic data generation
Training with Explanations Alone: A New Paradigm to Prevent Shortcut Learning
Semi-supervised 3D Object Detection with PatchTeacher and PillarMix
Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning
Layout-and-Retouch: A Dual-stage Framework for Improving Diversity in Personalized Image Generation
Graph Transformers: A Survey
Learning Weighted Finite Automata over the Max-Plus Semiring and its Termination
ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context
ICCV23 Visual-Dialog Emotion Explanation Challenge: SEU_309 Team Technical Report
LLM-Collaboration on Automatic Science Journalism for the General Audience

All 109